Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    text related to themes of judgment and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.71
    contentLoaded
    -0.61
    Personensuche
    -0.60
    VersionUID
    -0.57
    extAlignment
    -0.57
    AccessorTable
    -0.56
    HtmlAttribute
    -0.56
    libft
    -0.55
    obod
    -0.55
    parsedMessage
    -0.55
    POSITIVE LOGITS
     framing
    0.66
     framed
    0.65
     insult
    0.59
     insulted
    0.58
     syndicate
    0.58
     humiliated
    0.57
     frame
    0.56
     frames
    0.55
     insults
    0.55
     scolded
    0.55
    Act Density 0.082%

    No Known Activations